Mixed Kernel Research Articles

Strong robust state of health estimation of lithium-ion batteries based on aging feature mechanism analysis and improved mixed kernel least squares support vector regression model

Strong robust state of health estimation of lithium-ion batteries based on aging feature mechanism analysis and improved mixed kernel least squares support vector regression model

Multi-attribute balanced dataset generation framework AutoSyn and KinFace Channel-Spatial Feature Extractor for kinship recognition

In the field of kinship verification, facial recognition technology is becoming increasingly vital due to privacy concerns, ethical disputes, and the high costs associated with DNA testing. We have developed a novel method, the AutoSyn framework, to synthesize facial images and enhance kinship image datasets, effectively addressing the challenges of scale and quality in existing datasets. By employing a strategy that mixes ages and genders in the synthesized images, we minimize the impact of these factors on kinship recognition tasks. We have enhanced the original KinFaceW-I dataset by integrating ten distinct styles, including diverse combinations of gender, ethnicity, and age. This enrichment significantly improves both the quality and quantity of the images. Furthermore, this paper introduces an efficient feature extractor for kinship tasks, KinFace-CSFE, within a siamese neural network framework. This model not only utilizes meticulously designed channel feature extraction but also incorporates mixed kernel size spatial attention mechanisms to better focus on local features. We have also integrated YOCO data augmentation techniques to simulate complex imaging conditions, enhancing the model’s robustness and accuracy. The effectiveness of these innovations has been validated through experiments on the KinFaceW-I, KinFaceW-II, and synthesized Syn-KinFaceW-I datasets, achieving accuracy rates of 82.7%, 94.1%, and 83.2% respectively. These results significantly surpass both traditional models and current advanced models.

MILD combustion stabilization issues through the analysis of hysteresis behaviors: The case of new energy carriers

MILD combustion processes are renewed to reveal a strong resilience to extinction phenomena and/or instabilities, whereas the oxidation process is stabilized trough ignition phenomena. Under MILD conditions, igni-diffusive and/or perfectly mixed kernels, forming during the mixing process between hot products and fresh reactants, are so much diluted and pre-heated to escape classical feed-back flammable flames stabilization mechanisms, while ignition and extinction events merge in a unique condition through “anhysteretic” behaviors. So far, considering methane as reference fuel, it has been largely demonstrated the mentioned “anhysteretic” condition is very conservative and defines a sub-domain of MILD combustion processes, following Cavaliere and de Joannon's definition. Furthermore, the coincidence of ignition and extinction phenomena can occur also preserving hysteresis phenomena. In turns, this condition strongly enlarges the stabilization domain of MILD combustion processes, starting from the upper branch of the hysteresis behaviors to the real extinction, with characteristic unstable loci to consider as further/last opportunity to promote stable operative conditions through the formation of local thermo-kinetic conditions in the combustion chamber during hot products/fresh reactants mixing process (injection configuration/burner design), or by forced ignition events. The hysteresis behaviors of renewable/alternative fuels, relevant within the decarbonization policies of several energy sectors, are thoroughly discussed under MILD conditions through numerical studies in model reactors in order to shed light on common and/or different features, and outline practical rules towards the definition of stable MILD combustion domains. Results show that, as MILD combustion is a chemical kinetics-driven processes, stability issues have to be discussed in relation to fuel nature, albeit with common behavior can be derived. The coincidence between extinction/ignition phenomena is reached for extremely diluted conditions, already ascribable to MILD combustion conditions, thus defining a small sub-domain of the process. This condition can be reached through “hysteretic” or “anhysteretic” behaviors.

A deterministic and probabilistic hybrid model for wind power forecasting based improved feature screening and optimal Gaussian mixed kernel function

Forecasting wind power is crucial to ensuring the electricity system runs steadily. However, wind power forecasting is hampered by the randomness and volatility of wind power data. In this paper, a deterministic and probabilistic decomposition ensemble model based on improved feature screening and optimal Gaussian mixed kernel function is proposed, which mainly includes feature screening, feature learning, intelligent weighted integration and interval prediction modules. First, an improved feature screening (IFS) is proposed to capture the optimal features of the original wind power data, eliminating the interference of redundant features. Then an optimized deep neural network is suggested to learn the outcomes of IFS and further explore the temporal correlation of these features. Then, considering the difference of the contribution of each feature component, the final result is obtained by integrating the preliminary forecast results using intelligent weighted integration (IWI). Finally, an optimal mixed kernel-based Gaussian process regression model is developed for interval prediction, which improves the adaptability of the model. The data sets of two wind farms in Inner Mongolia were used for empirical testing. On the two datasets, the model's root mean square error (RMSE) is 1.1845 and 1.7354, respectively, both of which are lower than the comparison model. The model has the lowest coverage width criterion (CWC) of 0.1499 and 0.1460 on the two datasets, respectively.

Specific Emitter Identification through Multi-Domain Mixed Kernel Canonical Correlation Analysis

Radar specific emitter identification (SEI) involves extracting distinct fingerprints from radar signals to precisely attribute them to corresponding radar transmitters. In view of the limited characterization of fingerprint information by single-domain features, this paper proposes the utilization of multi-domain mixed kernel canonical correlation analysis for radar SEI. Initially, leveraging the complementarity across diverse feature domains, fingerprint features are extracted from four distinct domains including: envelope feature, spectrum feature, short-time Fourier transform and ambiguity function. Subsequently, kernel canonical correlation analysis is employed to amalgamate the correlation characteristics inherent in multi-domain data. Considering the insufficient of a single kernel function with only interpolation or extrapolation ability, we adopt mixed kernel to improve the projection ability of the kernel function. Experimental results substantiate that the proposed feature fusion approach maximizes the complementarity of multiple features while reducing feature dimensionality. The method achieves an accuracy of up to 95% in experiments, thereby enhancing the efficacy of radar SEI.

Using mixed kernel support vector machine to improve the predictive accuracy of genome selection1

The advantages of genome selection (GS) in animal and plant breeding are self-evident. Traditional parametric models have disadvantage in better fit the increasingly large sequencing data and capture complex effects accurately. Machine learning models have demonstrated remarkable potential in addressing these challenges. In this study, we introduced the concept of mixed kernel functions to explore the performance of support vector machine regression (SVR) in GS. Six single kernel functions (SVR_L, SVR_C, SVR_G, SVR_P, SVR_S, SVR_L) and four mixed kernel functions (SVR_GS, SVR_GP, SVR_LS, SVR_LP) were used to predict genome breeding values. The prediction accuracy, mean squared error (MSE) and mean absolute error (MAE) were used as evaluation indicators to compare with two traditional parametric models (GBLUP, BayesB) and two popular machine learning models (RF, KcRR). The results indicate that in most cases, the performance of the mixed kernel function model significantly outperforms that of GBLUP, BayesB and single kernel function. For instance, for T1 in the pig dataset, the predictive accuracy of SVR_GS is improved by 10% compared to GBLUP, and by approximately 4.4 and 18.6% compared to SVR_G and SVR_S respectively. For E1 in the wheat dataset, SVR_GS achieves 13.3% higher prediction accuracy than GBLUP. Among single kernel functions, the Laplacian and Gaussian kernel functions yield similar results, with the Gaussian kernel function performing better. The mixed kernel function notably reduces the MSE and MAE when compared to all single kernel functions. Furthermore, regarding runtime, SVR_GS and SVR_GP mixed kernel functions run approximately three times faster than GBLUP in the pig dataset, with only a slight increase in runtime compared to the single kernel function model. In summary, the mixed kernel function model of SVR demonstrates speed and accuracy competitiveness, and the model such as SVR_GS has important application potential for GS.

SOH Estimation for Lithium-Ion Batteries Based on Health Indicators Extraction and MKRVR

Aiming at the problems of difficult feature extraction and low State of Health (SOH) prediction accuracy of lithium-ion batteries, this paper proposes a SOH estimation approach that involves extracting Health Indicators (HIs) and utilizing mixed kernel function relevance vector regression (MKRVR). In order to accurately and efficiently extract battery HIs, the paper first examines the limitations of extracting HIs based on Incremental Capacity (IC) curves and puts forward an alternative method of HIs extraction based on voltage-capacity (V-C) curves. Following correlation analysis of the HIs, the paper establishes the MKRVR model that combines a range of kernel functions to estimate SOH. To determine the hyper-parameters and weight coefficients of the MKRVR model, the paper integrates Differential Evolution (DE) and Levy flight into the Gray Wolf Optimizer (GWO) to enhance the population diversity and random search ability of GWO. Finally, the paper conducts experimental validation utilizing three distinct battery datasets. The results indicate that the proposed approach outperforms Support Vector Regression (SVR) and Relevance Vector Regression (RVR), with evaluation index values of MAE, MSE, and RMSE all below 1%. Moreover, the coefficients of determination exceed 0.95, which demonstrates the superiority of this approach over other methods.

Black-box modeling of ship maneuvering motion using multi-output least-squares support vector regression based on optimal mixed kernel function

Black-box modeling has been widely used to predict ship maneuvering motion. A novel black-box modeling approach using optimal mixed kernel multi-output least-squares support vector regression (MMLSSVR) based on the artificial hummingbird algorithm (AHA) is proposed in this paper. To improve the performance of the MMLSSVR model, a mixed kernel function that combines a radial basis function and a polynomial kernel function to capture both global and local properties is proposed. The optimal hyper-parameters of the mixed kernel function are determined by the AHA, which employs the linear combination of the mean square error and the determinant of error covariance as the objective function to balance between prediction accuracy and stability. The performance of the proposed method is evaluated using SR108 large container ship data. The experimental results demonstrate that the proposed MMLSSVR model achieves desirable prediction accuracy and strong generalizability for ship maneuvering motion modeling.

Identification of reservoir types in deep carbonates based on mixed-kernel machine learning using geophysical logging data

Identification of reservoir types in deep carbonates has always been a great challenge due to complex logging responses caused by the heterogeneous scale and distribution of storage spaces. Traditional cross-plot analysis and empirical formula methods for identifying reservoir types using geophysical logging data have high uncertainty and low efficiency, which cannot accurately reflect the nonlinear relationship between reservoir types and logging data. Recently, the kernel Fisher discriminant analysis (KFD), a kernel-based machine learning technique, attracts attention in many fields because of its strong nonlinear processing ability. However, the overall performance of KFD model may be limited as a single kernel function cannot simultaneously extrapolate and interpolate well, especially for highly complex data cases. To address this issue, in this study, a mixed kernel Fisher discriminant analysis (MKFD) model was established and applied to identify reservoir types of the deep Sinian carbonates in central Sichuan Basin, China. The MKFD model was trained and tested with 453 datasets from 7 coring wells, utilizing GR, CAL, DEN, AC, CNL and RT logs as input variables. The particle swarm optimization (PSO) was adopted for hyper-parameter optimization of MKFD model. To evaluate the model performance, prediction results of MKFD were compared with those of basic-kernel based KFD, RF and SVM models. Subsequently, the built MKFD model was applied in a blind well test, and a variable importance analysis was conducted. The comparison and blind test results demonstrated that MKFD outperformed traditional KFD, RF and SVM in the identification of reservoir types, which provided higher accuracy and stronger generalization. The MKFD can therefore be a reliable method for identifying reservoir types of deep carbonates.

Multi-task Contexture Learning Network for automated vertebrae segmentation and tumor diagnosis from MRI

Automated vertebrae segmentation and tumor diagnosis from magnetic resonance imaging (MRI) scans play a crucial role in early detection of spinal tumors. However, the task is challenging due to the variability in fields of view across MRI images and the diverse appearances of tumors. To address these challenges, we propose a novel approach, the Multi-task Contexture Learning Network (MCLN), which concurrently performs accurate vertebrae segmentation and precise identification of tumors. Specifically, MCLN first constructs a spatial pyramid graph convolutional network and a label attention network to effectively capture long-range contextual information and generate a precise segmentation mask. Then, MCLN incorporates the input MRI image and the segmentation mask to recognize vertebral tumors utilizing a mixed kernel multi-loss network. We evaluate our proposed MCLN on a challenging dataset consisting of 600 MRI images, achieving impressive results with a mean Dice coefficient of 90.03% for vertebrae segmentation and a mean accuracy of 95.11% for tumor diagnosis. These results demonstrate the remarkable performance of MCLN in addressing automated vertebrae segmentation and tumor diagnosis from MRI.

MK-DCCA-Based Fault Diagnosis for Incipient Faults in Nonlinear Dynamic Processes

Incipient fault diagnosis is particularly important in process industrial systems, as its early detection helps to prevent major accidents. Against this background, this study proposes a combined method of mixed kernel principal components analysis and dynamic canonical correlation analysis (MK-DCCA). The robust generalization performance of this approach is demonstrated through experimental validation on a randomly generated dataset. Furthermore, comparative experiments were conducted on a CSTR Simulink model, comparing the MK-DCCA method with DCCA and DCVA methods, demonstrating its excellent detection performance for incipient faults in nonlinear and dynamic systems. Meanwhile, fault identification experiments were conducted, validating the high accuracy of the fault identification method based on contribution. The experimental findings demonstrate that the method possesses a certain industrial significance and academic relevance.

Fault detection and quantitative assessment of wheel diameter difference based on ensemble adaptive tunable Q-factor wavelet transform and mixed kernel principal component analysis

Tread wear is inevitable for railway vehicles. Because of the complicated railway condition, the wear rates of the two wheels of a wheelset are usually unequal, which leads to the wheel diameter difference (WDD). The WDD shortens the service life of the wheelset and deteriorates the dynamic performance of railway vehicles. Therefore, it has long been desired to monitor and quantify the WDD condition. However, influenced by the random irregularity, the effective vibration features induced by the WDD may be completely submerged in noise. In this paper, an adaptive TQWT decomposition method is proposed for denoise and feature enhancement. In this method, a new evaluation index is constructed and used to determine parameters. The influence of the WDD on the vibration of the wheelset can be more obvious after denoised by the adaptive TQWT decomposition. Mixed kernel principal component analysis is introduced into the condition monitoring and quantitative assessment of the WDD. By calculating the Hoteling’s and SPE statistics, control charts are employed to identify and assess the WDD conditions quantitatively in conjunction with the corresponding control limits. The effectiveness of the proposed method is validated by the simulation and experimental study. For the experimental datasets, the proposed method gives the average fault detection rate (FDR), false alarm rate (FAR), false alarm rate (PA) of 92.74%, 2.23%, 97.47% for the statistic and the average FDR, FAR, PA of 96.57%, 2.60%, 97.29% for the SPE statistic. The results show that the proposed method can effectively monitor the WDD conditions.

Improved deep mixed kernel randomized network for wind speed prediction

Abstract Forecasting wind speed is an extremely complicated and challenging problem due to its chaotic nature and its dependence on several atmospheric conditions. Although there are several intelligent techniques in the literature for wind speed prediction, their accuracies are not yet very reliable. Therefore, in this paper, a new hybrid intelligent technique named the deep mixed kernel random vector functional-link network auto-encoder (AE) is proposed for wind speed prediction. The proposed method eliminates manual tuning of hidden nodes with random weights and biases, providing prediction model generalization and representation learning. This reduces reconstruction error due to the exact inversion of the kernel matrix, unlike the pseudo-inverse in a random vector functional-link network, and shortens the execution time. Furthermore, the presence of a direct link from the input to the output reduces the complexity of the prediction model and improves the prediction accuracy. The kernel parameters and coefficients of the mixed kernel system are optimized using a new chaotic sine–cosine Levy flight optimization technique. The lowest errors in terms of mean absolute error (0.4139), mean absolute percentage error (4.0081), root mean square error (0.4843), standard deviation error (1.1431) and index of agreement (0.9733) prove the efficiency of the proposed model in comparison with other deep learning models such as deep AEs, deep kernel extreme learning machine AEs, deep kernel random vector functional-link network AEs, benchmark models such as least square support vector machine, autoregressive integrated moving average, extreme learning machines and their hybrid models along with different state-of-the-art methods.

Providing evidence for the conservation of a rare forest butterfly: Results from a three-year capture-mark-recapture study

Species living in spatially structured populations require a network of interconnected habitat patches. Due to changes in forest management, this network of habitat patches has been lost for insect species inhabiting open spots within forests. We studied two of the last populations of the Southern White Admiral (Limenitis reducta) in Germany. The aim of our study was to provide information for the conservation of this species. We conducted a capture-mark-recapture study over three consecutive years and we estimated population sizes and demographic parameters using Jolly-Seber and Cormack-Jolly-Seber models. Furthermore, we used different dispersal kernels to study the dispersal of L. reducta. We found that apparent survival rates differed greatly between the sexes. The mean residence times were eight to nine days for males and only two to four days for females. Apparent survival rates of both sexes decreased with increasing wing deterioration. Total population sizes of L. reducta varied between sites and years and ranged between 61 and 123. Daily abundances were generally low, especially that of females. The mean dispersal distance of individual recaptured butterflies increased in years with higher population densities, suggesting density-dependent dispersal. The dispersal data in our study was clearly bimodal, probably reflecting ‘routine movement’ at short distances and ‘displacement movement’ between habitat patches at longer distances. Consequently, the processes generating the dispersal data were better represented by the lognormal mixture model than by the negative exponential and the inverse power function. The mixed kernel predicted that about 9 % of the population disperses over > 1 km but that long-distance dispersal is rare. Our study highlights the urgent need for conservation measures to protect L. reducta in Germany and, based on our data, we recommend to create new habitat patches at distances of 1 to 1.5 km from existing habitats.

An enhanced decomposition integration model for deterministic and probabilistic carbon price prediction based on two-stage feature extraction and intelligent weight optimization

Accurately predicting carbon price can promote the rational allocation of carbon resources, reducing carbon emissions and contributing to green development. The decomposition integration framework is widely applied for carbon price forecasting, but several problems remain. Thus, this paper innovatively proposes an enhanced decomposition integration model for deterministic and probabilistic carbon price forecasting, which combines two-stage feature extraction and intelligent weight optimization. In order to decrease the complexity of the data and fully extract the characteristics, two decomposition approaches are utilized. For reconstruction, fuzzy entropy is applied to balance model complexity and computing efficiency. Next, the combination forecasting model based on two deep learning models is built to circumvent the constraints of the single forecasting model, and the cuckoo search optimization method (CS) is utilized to find the weight of the combination model adaptively. Considering the differences in the contributions of each component, the optimal weighting strategy based on CS is then used to derive the final forecast. Ultimately, considering the probability interval can provide more helpful information, the decomposition integration framework is supplemented with Gaussian process regression relying on the mixed kernel function for interval prediction. In an empirical study of five carbon trading markets, the hybrid model developed in this paper exceeded all baseline models regarding prediction stability, proving that the developed model can make effective forecasting for the carbon trading business.

Real-time anomaly data detection method based on mixed kernel function PSO-SVR

To avoid the influence of abnormal data of micro-plant factory sensors on the control system, an abnormal data detection method based on mixed kernel function particle swarm optimization (PSO)-support vector regression (SVR) is proposed. First, the mixed kernel function constructed by the polynomial kernel and radial basis kernel is used as the kernel function of SVR, and PSO is introduced to optimize the hyperparameters of the SVR model and establish a prediction model. Then, the model completes a step-by-step prediction based on the data in the sliding window and calculates confidence intervals. Finally, the data are judged to be abnormal based on whether the measured values exceed the confidence interval, and the abnormal values are replaced with the predicted values. The results show that the mean absolute percentage error of the model is 0.0063, the accuracy is 99.63%, the prediction accuracy and detection accuracy are better than the comparison model, and the abnormal data in the sensor data flow can be effectively detected and processed.

Efficient surface defect identification for optical components via multi-scale mixed Kernels and structural re-parameterization.

Surface defect identification plays a vital role in defective component rapid screening tasks in optics-related industries. However, the weakness and complexity of optical surface defects pose considerable challenges to their effective identification. To this end, a deep network based on multi-scale mixed kernels and structural re-parameterization is proposed to identify four manufacturing and two non-manufacturing optical surface defects. First, we design a multi-size mixed convolutional kernel with multiple receptive fields to extract rich shallow features for characterizing the defects with varying scales and irregular shapes. Then, we design an asymmetric mixed kernel integrating square, horizontal, vertical, and point convolutions to capture rotationally robust middle-and-deep features. Moreover, a structural re-parameterization strategy is introduced to equivalently convert the multi-branch architecture in the training phase into a deploy-friendly single-branch architecture in the inference phase, so that the model can obtain higher inference speed without losing any performance. Experiments on an optical surface defect dataset demonstrate that the proposed method is efficient and effective. It achieves a remarkable accuracy of 97.39% and an ultra-fast inference speed of 201.76 frames/second with only 5.23M parameters. Such a favorable accuracy-speed trade-off is capable of meeting the requirements of real-world optical surface defect identification applications.

Multi-parameter adaptive online energy management strategy for concrete truck mixers with a novel hybrid powertrain considering vehicle mass

Given the characteristics of dynamic vehicle mass, multi-operation scenes, and multi-energy-source and multi-energy-consumption-source, the energy optimization problem of concrete truck mixers remains a challenge. To this end, in this paper, a novel hybrid powertrain with a single-shaft parallel for the upper-part system and extended-range for the driving system is utilized and an adaptive online energy management strategy with multi parameters including the driving cycle, vehicle mass, battery state of charge (SOC), and remaining mileage is presented. First, a driven-data clustering method with fuel consumption differentiation is adopted. Then, using the parallel computing genetic algorithm-optimized rule-based method, a driving condition knowledge base, including optimal control models of the various typical driving conditions under multi-parameter combinations, is built to realize the adaptability and robustness. Parameter identifiers are designed, including a sparrow search-optimized-based deep mixed kernel extreme-learning machine recognizer and a vehicle mass recognizer based on sensor and working scene fusion for obtaining corresponding information online. Finally, simulation experiments are conducted to validate the performance and robustness of the presented control strategy. Results indicate it can reduce fuel consumption by an average value of 15.17% and performs better in the convergence level of terminal SOC in five real composite driving conditions.

Forecasting by Combining Chaotic PSO and Automated LSSVR

An automatic least square support vector regression (LSSVR) optimization method that uses mixed kernel chaotic particle swarm optimization (CPSO) to handle regression issues has been provided. The LSSVR model is composed of three components. The position of the particles (solution) in a chaotic sequence with good randomness and ergodicity of the initial characteristics is taken into consideration in the first section. The binary particle swarm optimization (PSO) used to choose potential input characteristic combinations makes up the second section. The final step involves using a chaotic search to narrow down the set of potential input characteristics before combining the PSO-optimized parameters to create CP-LSSVR. The CP-LSSVR is used to forecast the impressive datasets testing targets obtained from the UCI dataset for purposes of illustration and evaluation. The results suggest CP-LSSVR has a good predictive capability discussed in this paper and can build a projected model utilizing a limited number of characteristics.

A new trigonometric kernel function for support vector machine

In the last few years, various types of machine learning algorithms, such as Support Vector Machine (SVM), Support Vector Regression (SVR), and Non-negative Matrix Factorization (NMF) have been introduced. The kernel approach is an effective method for increasing the classification accuracy of machine learning algorithms. This paper introduces a family of one-parameter kernel functions for improving the accuracy of SVM classification. The proposed kernel function consists of a trigonometric term and differs from all existing kernel functions. We show this function is a positive definite kernel function. Finally, we evaluate the SVM method based on the new trigonometric kernel, the Gaussian kernel, the polynomial kernel, and a convex combination of the new kernel function and the Gaussian kernel function on various types of datasets. Empirical results show that the SVM based on the new trigonometric kernel function and the mixed kernel function achieve the best classification accuracy. Moreover, some numerical results of performing the SVR based on the new trigonometric kernel function and the mixed kernel function are presented.